Reil : a framework for reinforced intervention-based imitation learning | |
| Author | Rom Parnichkun |
| Call Number | AIT Thesis no.DSAI-22-01 |
| Subject(s) | Reinforcement learning Neural networks (Computer science) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Data Science and Artificial Intelligence |
| Publisher | Asian Institute of Technology |
| Abstract | Compared to traditional imitation learning methods such as DAgger and DART, inter vention based imitation offers a more convenient and sample efficient data collection process to users. In this thesis, we introduce Reinforced Intervention-based Learning (ReIL), a framework consisting of a general intervention-based learning algorithm and a multi-task imitation learning model aimed at enabling non-expert users to train agents in real environments with little supervision or fine tuning. ReIL achieves this with an algorithm that combines the advantages of imitation learning and reinforcement learn ing and a model named MimeticSNAIL, capable of concurrently processing demonstra tions, past experience, and current observations. Experimental results from real world mobile robot navigation challenges indicate that ReIL learns rapidly from sparse su pervisor corrections without suffering deterioration in performance that is character istic of supervised learning-based methods such as HG-Dagger and IWR. The results also demonstrate that in contrast to other intervention-based methods such as IARL and EGPO, ReIL can utilize an arbitrary reward function for training without any additional heuristics. |
| Year | 2022 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Data Science and Artificial Intelligence (DSAI) |
| Chairperson(s) | Dailey, Matthew N. |
| Examination Committee(s) | Mongkol Ekpanyapong |
| Scholarship Donor(s) | His Majesty the King’s Scholarships (Thailand) |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2022 |